Upload 10 files
Browse files- README.md +10 -3
- config.json +39 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantization_config.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Mistral v3 Tekken or Metharme.
|
| 2 |
+
|
| 3 |
+
Can think via \<thinking\> or \<think\>
|
| 4 |
+
|
| 5 |
+
Just like Roci X but better.
|
| 6 |
+
|
| 7 |
+
(Model card still a WIP)
|
| 8 |
+
|
| 9 |
+
FP16: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1
|
| 10 |
+
GGUF: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1-GGUF
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 54,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": null,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.45.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 131072,
|
| 27 |
+
"quantization_config": {
|
| 28 |
+
"quant_method": "exl3",
|
| 29 |
+
"version": "0.0.32",
|
| 30 |
+
"bits": 6.0,
|
| 31 |
+
"head_bits": 8,
|
| 32 |
+
"calibration": {
|
| 33 |
+
"rows": 250,
|
| 34 |
+
"cols": 2048
|
| 35 |
+
},
|
| 36 |
+
"out_scales": "always",
|
| 37 |
+
"codebook": "mcg"
|
| 38 |
+
}
|
| 39 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef696e39097087d8f4944c6619ab5f44a49652792fc733195ad1ecfe6127d7d9
|
| 3 |
+
size 8505777166
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73273a6f518542cc924b836b572d4aa34046abf45e419a19db527a343869d97b
|
| 3 |
+
size 4560182811
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantization_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|